#3044: Upgrade PCRE to 8.44

Foundation/src/pcre.h

@@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE_MAJOR          8
-#define PCRE_MINOR          43
+#define PCRE_MINOR          44
 #define PCRE_PRERELEASE
-#define PCRE_DATE           2019-02-23
+#define PCRE_DATE           020-02-12
 
 /* When an application links to a PCRE DLL in Windows, the symbols that are
 imported have to be identified as such. When building PCRE, the appropriate

Foundation/src/pcre_compile.c

@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2018 University of Cambridge
+           Copyright (c) 1997-2020 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -70,7 +70,7 @@ COMPILE_PCREx macro will already be appropriately set. */
 
 /* Macro for setting individual bits in class bitmaps. */
 
-#define SETBIT(a,b) a[(b)/8] |= (1 << ((b)&7))
+#define SETBIT(a,b) a[(b)/8] |= (1U << ((b)&7))
 
 /* Maximum length value to check against when making sure that the integer that
 holds the compiled pattern length does not overflow. We make it a bit less than
@@ -131,8 +131,8 @@ overrun before it actually does run off the end of the data block. */
 
 /* Private flags added to firstchar and reqchar. */
 
-#define REQ_CASELESS    (1 << 0)        /* Indicates caselessness */
+#define REQ_CASELESS    (1U << 0)        /* Indicates caselessness */
-#define REQ_VARY        (1 << 1)        /* Reqchar followed non-literal item */
+#define REQ_VARY        (1U << 1)        /* Reqchar followed non-literal item */
 /* Negative values for the firstchar and reqchar flags */
 #define REQ_UNSET       (-2)
 #define REQ_NONE        (-1)
@@ -3301,7 +3301,7 @@ for(;;)
       if ((*xclass_flags & XCL_MAP) == 0)
         {
         /* No bits are set for characters < 256. */
-        if (list[1] == 0) return TRUE;
+        if (list[1] == 0) return (*xclass_flags & XCL_NOT) == 0;
         /* Might be an empty repeat. */
         continue;
         }
@@ -3613,7 +3613,7 @@ for(;;)
       if (chr > 255) break;
       class_bitset = (pcre_uint8 *)
         ((list_ptr == list ? code : base_end) - list_ptr[2]);
-      if ((class_bitset[chr >> 3] & (1 << (chr & 7))) != 0) return FALSE;
+      if ((class_bitset[chr >> 3] & (1U << (chr & 7))) != 0) return FALSE;
       break;
 
 #if defined SUPPORT_UTF || !defined COMPILE_PCRE8
@@ -7132,17 +7132,19 @@ for (;; ptr++)
           int n = 0;
           ptr++;
           while(IS_DIGIT(*ptr))
+            {
             n = n * 10 + *ptr++ - CHAR_0;
+            if (n > 255)
+              {
+              *errorcodeptr = ERR38;
+              goto FAILED;
+              }
+            }
           if (*ptr != CHAR_RIGHT_PARENTHESIS)
             {
             *errorcodeptr = ERR39;
             goto FAILED;
             }
-          if (n > 255)
-            {
-            *errorcodeptr = ERR38;
-            goto FAILED;
-            }
           *code++ = n;
           PUT(code, 0, (int)(ptr - cd->start_pattern + 1)); /* Pattern offset */
           PUT(code, LINK_SIZE, 0);                          /* Default length */
@@ -7458,7 +7460,7 @@ for (;; ptr++)
               {
               open_capitem *oc;
               recno = GET2(slot, 0);
-              cd->backref_map |= (recno < 32)? (1 << recno) : 1;
+              cd->backref_map |= (recno < 32)? (1U << recno) : 1;
               if (recno > cd->top_backref) cd->top_backref = recno;
 
               /* Check to see if this back reference is recursive, that it, it
@@ -7644,8 +7646,8 @@ for (;; ptr++)
         /* Can't determine a first byte now */
 
         if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE;
-		zerofirstchar = firstchar;
+        zerofirstchar = firstchar;
-		zerofirstcharflags = firstcharflags;
+        zerofirstcharflags = firstcharflags;
         continue;
 
 
@@ -8069,7 +8071,7 @@ for (;; ptr++)
         item_hwm_offset = cd->hwm - cd->start_workspace;
         *code++ = ((options & PCRE_CASELESS) != 0)? OP_REFI : OP_REF;
         PUT2INC(code, 0, recno);
-        cd->backref_map |= (recno < 32)? (1 << recno) : 1;
+        cd->backref_map |= (recno < 32)? (1U << recno) : 1;
         if (recno > cd->top_backref) cd->top_backref = recno;
 
         /* Check to see if this back reference is recursive, that it, it
@@ -8682,7 +8684,7 @@ do {
             op == OP_SCBRA || op == OP_SCBRAPOS)
      {
      int n = GET2(scode, 1+LINK_SIZE);
-     int new_map = bracket_map | ((n < 32)? (1 << n) : 1);
+     int new_map = bracket_map | ((n < 32)? (1U << n) : 1);
      if (!is_anchored(scode, new_map, cd, atomcount)) return FALSE;
      }
 
@@ -8694,6 +8696,7 @@ do {
      }
 
    /* Condition; not anchored if no second branch */
+
    else if (op == OP_COND)
      {
      if (scode[GET(scode,1)] != OP_ALT) return FALSE;
@@ -8809,7 +8812,7 @@ do {
             op == OP_SCBRA || op == OP_SCBRAPOS)
      {
      int n = GET2(scode, 1+LINK_SIZE);
-     int new_map = bracket_map | ((n < 32)? (1 << n) : 1);
+     int new_map = bracket_map | ((n < 32)? (1U << n) : 1);
      if (!is_startline(scode, new_map, cd, atomcount, inassert)) return FALSE;
      }
 

Foundation/src/pcre_config.h

@@ -289,7 +289,7 @@ sure both macros are undefined; an emulation function will then be used. */
 #define PACKAGE_NAME "PCRE"
 
 /* Define to the full name and version of this package. */
-#define PACKAGE_STRING "PCRE 8.43"
+#define PACKAGE_STRING "PCRE 8.44"
 
 /* Define to the one symbol short name of this package. */
 #define PACKAGE_TARNAME "pcre"
@@ -298,7 +298,7 @@ sure both macros are undefined; an emulation function will then be used. */
 #define PACKAGE_URL ""
 
 /* Define to the version of this package. */
-#define PACKAGE_VERSION "8.43"
+#define PACKAGE_VERSION "8.44"
 
 /* The value of PARENS_NEST_LIMIT specifies the maximum depth of nested
    parentheses (of any kind) in a pattern. This limits the amount of system
@@ -400,7 +400,7 @@ sure both macros are undefined; an emulation function will then be used. */
 /* #undef SUPPORT_VALGRIND */
 
 /* Version number of package */
-#define VERSION "8.43"
+#define VERSION "8.44"
 
 /* Define to empty if `const' does not conform to ANSI C. */
 /* #undef const */

Foundation/src/pcre_jit_compile.c

@@ -3937,10 +3937,10 @@ static sljit_s32 character_to_int32(pcre_uchar chr)
 sljit_s32 value = (sljit_s32)chr;
 #if defined COMPILE_PCRE8
 #define SSE2_COMPARE_TYPE_INDEX 0
-return (value << 24) | (value << 16) | (value << 8) | value;
+return ((unsigned int)value << 24) | ((unsigned int)value << 16) | ((unsigned int)value << 8) | (unsigned int)value;
 #elif defined COMPILE_PCRE16
 #define SSE2_COMPARE_TYPE_INDEX 1
-return (value << 16) | value;
+return ((unsigned int)value << 16) | value;
 #elif defined COMPILE_PCRE32
 #define SSE2_COMPARE_TYPE_INDEX 2
 return value;
@@ -8506,7 +8506,7 @@ if (opcode == OP_ONCE)
   /* We temporarily encode the needs_control_head in the lowest bit.
      Note: on the target architectures of SLJIT the ((x << 1) >> 1) returns
      the same value for small signed numbers (including negative numbers). */
-  BACKTRACK_AS(bracket_backtrack)->u.framesize = (BACKTRACK_AS(bracket_backtrack)->u.framesize << 1) | (needs_control_head ? 1 : 0);
+  BACKTRACK_AS(bracket_backtrack)->u.framesize = ((unsigned int)BACKTRACK_AS(bracket_backtrack)->u.framesize << 1) | (needs_control_head ? 1 : 0);
   }
 return cc + repeat_length;
 }
@@ -9001,7 +9001,7 @@ if (exact > 1)
 #ifdef SUPPORT_UTF
       && !common->utf
 #endif
-      )
+      && type != OP_ANYNL && type != OP_EXTUNI)
     {
     OP2(SLJIT_ADD, TMP1, 0, STR_PTR, 0, SLJIT_IMM, IN_UCHARS(exact));
     add_jump(compiler, &backtrack->topbacktracks, CMP(SLJIT_GREATER, TMP1, 0, STR_END, 0));